{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07920792079207921,
      "grad_norm": 1.8944026231765747,
      "learning_rate": 0.0,
      "loss": 2.8705,
      "step": 1
    },
    {
      "epoch": 0.15841584158415842,
      "grad_norm": 1.8068678379058838,
      "learning_rate": 2e-05,
      "loss": 2.6876,
      "step": 2
    },
    {
      "epoch": 0.2376237623762376,
      "grad_norm": 1.9159170389175415,
      "learning_rate": 4e-05,
      "loss": 2.8577,
      "step": 3
    },
    {
      "epoch": 0.31683168316831684,
      "grad_norm": 1.672847867012024,
      "learning_rate": 6e-05,
      "loss": 2.7788,
      "step": 4
    },
    {
      "epoch": 0.39603960396039606,
      "grad_norm": 1.6339856386184692,
      "learning_rate": 8e-05,
      "loss": 2.688,
      "step": 5
    },
    {
      "epoch": 0.4752475247524752,
      "grad_norm": 1.4535776376724243,
      "learning_rate": 0.0001,
      "loss": 2.5674,
      "step": 6
    },
    {
      "epoch": 0.5544554455445545,
      "grad_norm": 1.4043422937393188,
      "learning_rate": 9.705882352941177e-05,
      "loss": 2.5515,
      "step": 7
    },
    {
      "epoch": 0.6336633663366337,
      "grad_norm": 1.38013756275177,
      "learning_rate": 9.411764705882353e-05,
      "loss": 2.478,
      "step": 8
    },
    {
      "epoch": 0.7128712871287128,
      "grad_norm": 1.188214898109436,
      "learning_rate": 9.11764705882353e-05,
      "loss": 2.3253,
      "step": 9
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 1.2095648050308228,
      "learning_rate": 8.823529411764706e-05,
      "loss": 2.2612,
      "step": 10
    },
    {
      "epoch": 0.8712871287128713,
      "grad_norm": 1.3112112283706665,
      "learning_rate": 8.529411764705883e-05,
      "loss": 2.2516,
      "step": 11
    },
    {
      "epoch": 0.9504950495049505,
      "grad_norm": 1.1764588356018066,
      "learning_rate": 8.23529411764706e-05,
      "loss": 2.2492,
      "step": 12
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.4241539239883423,
      "learning_rate": 7.941176470588235e-05,
      "loss": 2.2301,
      "step": 13
    },
    {
      "epoch": 1.0792079207920793,
      "grad_norm": 1.2298003435134888,
      "learning_rate": 7.647058823529411e-05,
      "loss": 2.3024,
      "step": 14
    },
    {
      "epoch": 1.1584158415841583,
      "grad_norm": 1.0761587619781494,
      "learning_rate": 7.352941176470589e-05,
      "loss": 2.1472,
      "step": 15
    },
    {
      "epoch": 1.2376237623762376,
      "grad_norm": 1.0203983783721924,
      "learning_rate": 7.058823529411765e-05,
      "loss": 2.1082,
      "step": 16
    },
    {
      "epoch": 1.316831683168317,
      "grad_norm": 1.159624457359314,
      "learning_rate": 6.764705882352942e-05,
      "loss": 2.173,
      "step": 17
    },
    {
      "epoch": 1.396039603960396,
      "grad_norm": 1.0887689590454102,
      "learning_rate": 6.470588235294118e-05,
      "loss": 2.0336,
      "step": 18
    },
    {
      "epoch": 1.4752475247524752,
      "grad_norm": 1.0648787021636963,
      "learning_rate": 6.176470588235295e-05,
      "loss": 1.989,
      "step": 19
    },
    {
      "epoch": 1.5544554455445545,
      "grad_norm": 1.1488330364227295,
      "learning_rate": 5.882352941176471e-05,
      "loss": 2.0637,
      "step": 20
    },
    {
      "epoch": 1.6336633663366338,
      "grad_norm": 1.0536024570465088,
      "learning_rate": 5.588235294117647e-05,
      "loss": 2.1311,
      "step": 21
    },
    {
      "epoch": 1.7128712871287128,
      "grad_norm": 1.1403701305389404,
      "learning_rate": 5.294117647058824e-05,
      "loss": 2.0831,
      "step": 22
    },
    {
      "epoch": 1.7920792079207921,
      "grad_norm": 1.107954740524292,
      "learning_rate": 5e-05,
      "loss": 2.09,
      "step": 23
    },
    {
      "epoch": 1.8712871287128712,
      "grad_norm": 1.0495295524597168,
      "learning_rate": 4.705882352941177e-05,
      "loss": 2.0811,
      "step": 24
    },
    {
      "epoch": 1.9504950495049505,
      "grad_norm": 1.0435138940811157,
      "learning_rate": 4.411764705882353e-05,
      "loss": 2.0862,
      "step": 25
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.3227992057800293,
      "learning_rate": 4.11764705882353e-05,
      "loss": 1.9347,
      "step": 26
    },
    {
      "epoch": 2.0792079207920793,
      "grad_norm": 0.9908578395843506,
      "learning_rate": 3.8235294117647055e-05,
      "loss": 2.0467,
      "step": 27
    },
    {
      "epoch": 2.1584158415841586,
      "grad_norm": 1.0480220317840576,
      "learning_rate": 3.529411764705883e-05,
      "loss": 1.967,
      "step": 28
    },
    {
      "epoch": 2.237623762376238,
      "grad_norm": 1.0408047437667847,
      "learning_rate": 3.235294117647059e-05,
      "loss": 1.9491,
      "step": 29
    },
    {
      "epoch": 2.3168316831683167,
      "grad_norm": 1.163356065750122,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 1.9574,
      "step": 30
    },
    {
      "epoch": 2.396039603960396,
      "grad_norm": 1.0859148502349854,
      "learning_rate": 2.647058823529412e-05,
      "loss": 1.8265,
      "step": 31
    },
    {
      "epoch": 2.4752475247524752,
      "grad_norm": 1.0860532522201538,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 1.8592,
      "step": 32
    },
    {
      "epoch": 2.5544554455445545,
      "grad_norm": 1.0774939060211182,
      "learning_rate": 2.058823529411765e-05,
      "loss": 1.9709,
      "step": 33
    },
    {
      "epoch": 2.633663366336634,
      "grad_norm": 1.0513403415679932,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 1.842,
      "step": 34
    },
    {
      "epoch": 2.7128712871287126,
      "grad_norm": 1.0179636478424072,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 1.9262,
      "step": 35
    },
    {
      "epoch": 2.792079207920792,
      "grad_norm": 1.1298041343688965,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.9929,
      "step": 36
    },
    {
      "epoch": 2.871287128712871,
      "grad_norm": 1.1205837726593018,
      "learning_rate": 8.823529411764707e-06,
      "loss": 1.8582,
      "step": 37
    },
    {
      "epoch": 2.9504950495049505,
      "grad_norm": 1.1293277740478516,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.9963,
      "step": 38
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.5077970027923584,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 1.9583,
      "step": 39
    }
  ],
  "logging_steps": 1,
  "max_steps": 39,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1791632051251200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}